© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129598
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    C
    -2.17
    N
    -2.11
    K
    -2.03
    T
    -1.85
    B
    -1.84
    '
    -1.70
    H
    -1.69
     retrô
    -1.69
    e
    -1.68
    F
    -1.67
    POSITIVE LOGITS
     are
    1.91
     they
    1.85
    ꯳
    1.58
     sekarang
    1.57
    CCIÓN
    1.56
     وزن
    1.53
    unched
    1.52
    trucks
    1.48
    前は
    1.48
    Millisecond
    1.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.